Parallel Latent Reasoning for Sequential Recommendation

TL;DR

This paper introduces Parallel Latent Reasoning (PLR), a novel framework for sequential recommendation that explores multiple reasoning paths simultaneously, significantly improving recommendation accuracy and efficiency.

Contribution

PLR pioneers width-level computational scaling in sequential recommendation by enabling multiple diverse reasoning streams through learnable trigger tokens and regularization.

Findings

PLR outperforms state-of-the-art methods on three real-world datasets.

PLR maintains real-time inference efficiency despite increased reasoning complexity.

Theoretical analysis confirms improved generalization with parallel reasoning.

Abstract

Capturing complex user preferences from sparse behavioral sequences remains a fundamental challenge in sequential recommendation. Recent latent reasoning methods have shown promise by extending test-time computation through multi-step reasoning, yet they exclusively rely on depth-level scaling along a single trajectory, suffering from diminishing returns as reasoning depth increases. To address this limitation, we propose \textbf{Parallel Latent Reasoning (PLR)}, a novel framework that pioneers width-level computational scaling by exploring multiple diverse reasoning trajectories simultaneously. PLR constructs parallel reasoning streams through learnable trigger tokens in continuous latent space, preserves diversity across streams via global reasoning regularization, and adaptively synthesizes multi-stream outputs through mixture-of-reasoning-streams aggregation. Extensive experiments on three real-world datasets demonstrate that PLR substantially outperforms state-of-the-art baselines while maintaining real-time inference efficiency. Theoretical analysis further validates the effectiveness of parallel reasoning in improving generalization capability. Our work opens new avenues for enhancing reasoning capacity in sequential recommendation beyond existing depth scaling.